CharlesLi
/

OpenELM-1_1B-DPO-full-max-4-reward

Text Generation

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

OpenELM-1_1B-DPO-full-max-4-reward / runs /Oct07_05-34-25_xe8545-a100-22

1 contributor

History: 1 commit

CharlesLi's picture

Model save

aeb82f8 verified about 2 months ago

events.out.tfevents.1728272702.xe8545-a100-22.2437144.0

231 kB
LFS

Model save about 2 months ago